跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-13AI 評分45

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

AI 導讀

AesCode以解耦的跨模態獎勵進行強化學習,提升程式碼生成視覺作品的空間規劃、美感及可驗證正確性。相較使用相同參考圖像的同規模 Qwen3-VL 基線,AesCode-8B 和 AesCode-32B 的視覺品質分數分別提高 31.1 和 22.4 個百分點,達到與 GPT-5.5、Claude Opus 4.8 等閉源前沿模型相若的水平。

正文

Published on Oct 13

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable, and verifiable. Yet code models cannot see how their choices of layout and color come together on the canvas, often limiting spatial planning and aesthetic quality. Image generators excel at visual design but can misrender requested content, making their outputs unreliable targets for direct reproduction. We therefore introduce AesCode, which generates code grounded in the content prompt while using an image generated from the same prompt as an aesthetic guidance. To do so, AesCode represents the target as a design graph that describes the whole canvas and makes each property attributable. From this graph, we derive complementary cross-modal rewards: deterministic verifiers score properties parsable from code and rendering, while a VLM judge assesses the non-parsable ones with a sample-specific Visual Graph Rubric (VGR) tied to graph elements and relations. We optimize these decoupled rewards through reinforcement learning with per-channel normalization to jointly improve spatial planning, aesthetic quality, and verifiable correctness. To evaluate this setting, we build a benchmark that scores verifiable correctness and visual quality separately, with visual scores highly consistent with human judgments. We find that reference images substantially improve the visual quality of code generated by existing models, and ablations show that AesCode benefits from references both as model input and as a source of visual rewards. Relative to same-scale Qwen3-VL baselines given the same references, AesCode-8B and AesCode-32B improve visual quality by 31.1 and 22.4 percentage points, reaching scores comparable to those of closed-source frontier models such as GPT-5.5 and Claude Opus 4.8.

View arXiv page View PDF Project page GitHub 42 Add to collection

Get this paper in your agent:

hf papers read 2610.18860

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.18860 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.18860 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.18860 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co